Open Models Almanac
Methodssoftware implementationtraining framework

specific method · filed under software implementation

Hugging Face Transformers

The Transformers library is used for model inference and related model operations.

The sources on this page name it without explaining how it works. The line above is the extraction's one-line gloss. See training framework for the methods filed beside it.

Also called Transformers, HuggingFace Transformers.

sources
4
models
3
labs adopt it
3
strongest
used

Documented in

Evidence

4 quotes from 4 sources, one card per model, each opening with its strongest.

How sources treat it
optional 3used 1

NVIDIA-Nemotron-3-Ultra-550B-A55B

NVIDIAadopted2 sources

We used transformers on a single node with CPU offloading to quantize Ultra layer-by-layer.

usedsoftware implementationin Nemotron 3 UltraNVIDIA
1 more from this model

Model-Optimizer’s HuggingFace PTQ script uses transformers native inference

optionalsoftware implementationin Nemotron 3 Ultra

MiniMax-M3

MiniMaxadopted1 source

We recommend the following inference frameworks to serve the model: Transformers

optionalsoftware implementationin MiniMax-M3MiniMax

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

↑